Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    exclamation marks and related punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX math notation

    np_acts-logits-general · gemini-2.0-flash

    $\approx\ ! \text{ } \langle \text{ } = \text{ } \text{rm}$

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >−
    -0.54
    ret
    -0.52
    en
    -0.52
    <eos>
    -0.51
     kasarigan
    -0.49
     surla
    -0.49
    RegressionTest
    -0.47
    ia
    -0.47
    SharedCtor
    -0.46
    so
    -0.46
    POSITIVE LOGITS
    gherita
    0.72
    FundMe
    0.71
    urator
    0.69
    ressee
    0.69
     ReSharper
    0.69
    ercice
    0.69
    rinol
    0.68
    unzel
    0.68
     whiteColor
    0.67
     FileNotFound
    0.66
    Act Density 0.157%

    No Known Activations